多个基因对应一个探针

1. 全部symbol都保存

library(tidyverse)
## ── Attaching packages ───────────────────────────── tidyverse 1.2.1 ──
## ✔ ggplot2 3.1.0     ✔ purrr   0.2.5
## ✔ tibble  1.4.2     ✔ dplyr   0.7.8
## ✔ tidyr   0.8.2     ✔ stringr 1.3.1
## ✔ readr   1.3.0     ✔ forcats 0.3.0
## ── Conflicts ──────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
(a <- tibble(probe = c("101a","102a","103a"),symbol = c("aad///ddd",'bbb',"aad///ddv///xxx")))
## # A tibble: 3 x 2
##   probe symbol         
##   <chr> <chr>          
## 1 101a  aad///ddd      
## 2 102a  bbb            
## 3 103a  aad///ddv///xxx
(test1 <- apply(a,
              1,
              function(x){
                str_split(x[2],'///',simplify=T)
}))
## [[1]]
##      [,1]  [,2] 
## [1,] "aad" "ddd"
## 
## [[2]]
##      [,1] 
## [1,] "bbb"
## 
## [[3]]
##      [,1]  [,2]  [,3] 
## [1,] "aad" "ddv" "xxx"
(test2 <- apply(a,
               1,
               function(x){
                 paste(x[1],
                 str_split(x[2],'///',simplify=T),
                 sep = "...")
               }))
## [[1]]
## [1] "101a...aad" "101a...ddd"
## 
## [[2]]
## [1] "102a...bbb"
## 
## [[3]]
## [1] "103a...aad" "103a...ddv" "103a...xxx"
unlist(test2)
## [1] "101a...aad" "101a...ddd" "102a...bbb" "103a...aad" "103a...ddv"
## [6] "103a...xxx"
(x <- tibble(unlist(test2))) 
## # A tibble: 6 x 1
##   `unlist(test2)`
##   <chr>          
## 1 101a...aad     
## 2 101a...ddd     
## 3 102a...bbb     
## 4 103a...aad     
## 5 103a...ddv     
## 6 103a...xxx
colnames(x) <- "lala" 
(x2 <- separate(x,lala,c("id","symbol")))
## # A tibble: 6 x 2
##   id    symbol
##   <chr> <chr> 
## 1 101a  aad   
## 2 101a  ddd   
## 3 102a  bbb   
## 4 103a  aad   
## 5 103a  ddv   
## 6 103a  xxx

# 上面是针对转录组可以直接这样，但是探针的话，因为中间存在_，所以代码可以改变如下
test2 <- apply(ids,
               1,
               function(x){
                 paste(x[1],
                 str_split(x[2],'///',simplify=T),
                 sep = "...")
               })
x = tibble(unlist(test2))

colnames(x) <- "lala" 
ids <- separate(x,lala,c("ID","symbol"),sep = "\\...")

2. 只保存symbol第一个